Joint-product representation learning for domain generalization in classification and regression
Joint-product representation learning for domain generalization in classification and regression
复制标题
DOI：
10.1007/s00521-023-08520-1
复制
发表时间：
2023-04
影响因子：
6
通讯作者：
Sentao Chen;Liang Chen
中科院分区：
文献类型：
--
作者：
Sentao Chen;Liang Chen
在这项工作中，我们研究将在一组源域上训练的预测（分类或回归）模型泛化到不可见的目标域的问题，其中源域和目标域不同但相关，即域泛化问题。该问题的挑战在于域差异，这可能会降低预测模型的泛化能力。为了应对这一挑战，我们建议学习神经网络表示函数来对齐表示空间中的联合分布和乘积分布，并表明这种联合乘积分布对齐可以方便地导致多个域的对齐。特别是，我们在距离下对齐联合分布和乘积分布，并表明可以通过利用其变分特征和线性变分函数来分析估计该距离。这使我们能够通过最小化相对于网络表示函数的估计距离来轻松地对齐两个分布。我们对用于分类和回归的合成和真实数据集进行的实验证明了所提出的解决方案的有效性。例如，它在文本数据集 Amazon Reviews 上实现了 82.26% 的最佳平均分类精度，在 WiFi 数据集 UJIIndoorLoc 上实现了 0.114 的最佳平均回归误差。
In this work, we study the problem of generalizing a prediction (classification or regression) model trained on a set of source domains to an unseen target domain, where the source and target domains are different but related,i.e, the domain generalization problem. The challenge in this problem lies in the domain difference, which could degrade the generalization ability of the prediction model. To tackle this challenge, we propose to learn a neural network representation function to align a joint distribution and a product distribution in the representation space, and show that such joint-product distribution alignment conveniently leads to the alignment of multiple domains. In particular, we align the joint distribution and the product distribution under the-distance, and show that this distance can be analytically estimated by exploiting its variational characterization and a linear variational function. This allows us to comfortably align the two distributions by minimizing the estimated distance with respect to the network representation function. Our experiments on synthetic and real-world datasets for classification and regression demonstrate the effectiveness of the proposed solution. For example, it achieves the best average classification accuracy of 82.26% on the text dataset Amazon Reviews, and the best average regression error of 0.114 on the WiFi dataset UJIIndoorLoc.